آموزش استخراج داده (Scrape) از Seeking Alpha: داده‌های مالی و ترانسکریپت‌ها

from playwright.sync_api import sync_playwright

def run(playwright):
    # Launching a Chromium browser
    browser = playwright.chromium.launch(headless=True)
    context = browser.new_context(
        user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
    )
    page = context.new_page()
    
    try:
        # Navigating to a specific stock symbol page
        page.goto('https://seekingalpha.com/symbol/AAPL/transcripts')
        
        # Wait for the main content to render dynamically
        page.wait_for_selector('article', timeout=15000)
        
        # Locate and extract transcript titles
        titles = page.locator('h3').all_inner_texts()
        for title in titles:
            print(f'Found Transcript: {title}')
            
    except Exception as e:
        print(f'Extraction failed: {e}')
    finally:
        browser.close()

with sync_playwright() as playwright:
    run(playwright)

import scrapy

class SeekingAlphaSpider(scrapy.Spider):
    name = 'sa_spider'
    allowed_domains = ['seekingalpha.com']
    start_urls = ['https://seekingalpha.com/latest-articles']

    custom_settings = {
        'DOWNLOAD_DELAY': 8,
        'USER_AGENT': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/120.0.0.0',
        'ROBOTSTXT_OBEY': False,
        'COOKIES_ENABLED': True
    }

    def parse(self, response):
        for article in response.css('article'):
            yield {
                'title': article.css('h3 a::text').get(),
                'link': response.urljoin(article.css('h3 a::attr(href)').get()),
                'author': article.css('span[data-test-id="author-name"]::text').get()
            }

        # Handle simple pagination via 'next' links
        next_page = response.css('a.next_page::attr(href)').get()
        if next_page:
            yield response.follow(next_page, self.parse)

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch({ headless: true });
  const page = await browser.newPage();
  
  // Set high-quality User-Agent
  await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36');
  
  try {
    // Navigate to Seeking Alpha homepage
    await page.goto('https://seekingalpha.com/', { waitUntil: 'networkidle2' });
    
    // Evaluate scripts in the browser context to extract titles
    const trending = await page.evaluate(() => {
      const nodes = Array.from(document.querySelectorAll('h3'));
      return nodes.map(n => n.innerText.trim());
    });

    console.log('Trending Content:', trending);
  } catch (err) {
    console.error('Puppeteer encountered an error:', err);
  } finally {
    await browser.close();
  }
})();